Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Lunch and Poster Display session

69P - Deep learning prognostication through prediction of TP53 gene mutation status on breast cancer hematoxylin and eosin slides

Date

16 May 2024

Session

Lunch and Poster Display session

Presenters

Nikolaos Tsiknakis

Citation

Annals of Oncology (2024) 9 (suppl_4): 1-34. 10.1016/esmoop/esmoop103010

Authors

N. Tsiknakis1, D. Salgkamis2, E. Tzoras2, K. Wang2, X. Liu3, G. Manikis2, E.G. Sifakis2, J. Bergh2, K. Marias4, I. Zerdes2, A. Matikas5, T. Foukakis2

Author affiliations

  • 1 Karolinska Institute, Solna/SE
  • 2 Karolinska Institutet, Stockholm/SE
  • 3 Karolinska Institutet, Solna/SE
  • 4 Foundation for Research and Technology - Hellas (FORTH), Heraklion/GR
  • 5 karolinska Institutet - Stockholm, Stockholm/SE

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 69P

Background

TP53 gene plays a crucial role in cell functions, such as proliferation, survival, and maintaining genomic integrity. In breast cancer, TP53 mutations are associated with worse prognosis. The pivotal role of p53 in tumor development suggests that morphological features in H&E-stained tumor tissue sections may be distinctive for the presence of mutation. The aim of this study is to develop an artificial intelligence (AI) model for predicting TP53 mutations to be used for patient prognostication.

Methods

We trained an ER-stratified deep learning model on surgical H&E-stained tissue sections for predicting TP53 gene mutation status on TCGA-BRCA (N=943). We validated its ability to predict TP53 mutations and its prognostic performance on an external validation cohort (N=207 patients primarily treated in Uppsala, Sweden, 1987-1989). TP53 mutations were observed in 30.9% (NGS) of the individuals, with rates of 19% and 72.7% in the ER+ and ER- subgroups in TCGA; external cohort mutation rates were 22.7% overall (Sanger sequencing), 17.4% for the ER+ and 47.4% for the ER- subgroups. A Convolutional Neural Network pretrained on ImageNet was used to extract features from the tissue slides, while a multiple instance learning classifier was trained for mutation status prediction based on bags of instances of the extracted imaging features. ROC curve analysis was used for optimal cut-off estimation.

Results

The model achieved an overall AUC of 0.76 on the validation set, reaching 0.74 and 0.77 for ER+ and ER- subgroups respectively. Digital TP53 prediction was significantly prognostic with respect to overall survival in univariate (HR=1.7, 95% CI: 1.1-2.5, p=0.019) and multivariate analyses (HR=2.1, 95% CI: 1.3-3.4, p=0.002) after adjusting for ER, age, size, nodal and HER2 status. Additional results on external validation cohorts are ongoing and will be presented.

Conclusions

We developed and validated an AI model that showed promise as a cost-effective and robust alternative surrogate method to predict TP53 mutation status on H&E-stained tissue sections in breast cancer. The model's prognostic value independent of established prognostic clinical factors highlights its potential clinical relevance as a digital biomarker.

Legal entity responsible for the study

The authors.

Funding

Swedish research council and Swedish cancer society.

Disclosure

J. Bergh: Other, Fees (honoraria) to Coronis and Asklepios Cancer Research AB as an invited speaker/chair from AstraZeneca and Roche, respectively: Coronis and Asklepios Cancer Research AB.; Other, Institutional honoraria as chapter co-author for UpToDate to Asklepios Medicin HB. Co-author on a chapter on ”Prognostic and Predictive factors in early, non-metastatic breast cancer”: Asklepios Medicin; Other, Institutional research grants received more than ten years ago to Karolinska Institutet and/or University Hospital for molecular marker studies/ clinical studies (we are still working with the material). No personal payments for these activities: Amgen, AstraZeneca, Bayer, Merck, Pfizer, Roche and Sanofi-Aventis; Other, Stocks in Stratipath AB. The company is involved in AI based diagnostics for breast cancer: Stratipath AB. A. Matikas: Financial Interests, Institutional, Invited Speaker: Seagen; Financial Interests, Institutional, Invited Speaker, International co-PI of academic trial ARIADNE (EU CT: 2022-501504-95-00): AstraZeneca, Novartis, Veracyte; Financial Interests, Institutional, Invited Speaker, Registry study: Merck; Non-Financial Interests, Advisory Role: Veracyte, Roche. T. Foukakis: Financial Interests, Institutional, Invited Speaker: Roche, AstraZeneca, Gilead Sciences; Financial Interests, Personal, Royalties, Authorship of two chapters in UpToDate: Wolters Kluwer; Financial Interests, Institutional, Invited Speaker, Clinical trial support (research grant and study drug): AstraZeneca; Financial Interests, Institutional, Invited Speaker, Clinical trial support (research grant and study drug): Novartis; Financial Interests, Institutional, Invited Speaker, Discount on the Prosigna PAM50 assay in ARIADNE clinical trial: Veracyte. All other authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.